modelTieParam: Tie parameters of a model together.

In ahonkela/tigre: Transcription factor Inference through Gaussian process Reconstruction of Expression

Description

groups of parameters of a model to be seen as one parameter during optimisation of the model.

Usage

  modelTieParam(model, paramsList)

Arguments

model

the model for which parameters are being tied together.

paramsList

indices of parameteres to group together. The indices are provided in a list. Each element in the list contains a vector of indices of parameters that should be considered as one parameter. Each group of parameters in each cell should obviously be mutually exclusive. Alternatively, the specification may consist of strings, which are interpreted as regular expressions that are matched against the parameter names returned by modelExtractParam or kernExtractParam, as appropriate fot the current object.

Value

model

the model with the parameters grouped together.

See Also

modelExtractParam, modelExpandParam, modelGradient.

Examples

# Create a multi kernel with two rbf blocks with bounded inverse widths
invWidthBounds <- c(0.5, 2)
kernType <- list(type="multi", comp=list())
for (i in 1:2)
  kernType$comp[[i]] <- list(type="parametric", realType="rbf",
                              options=list(isNormalised=TRUE,
                                inverseWidthBounds=invWidthBounds))
kern <- kernCreate(1, kernType)

# Tie the inverse with parameters of the component RBF kernels
kern <- modelTieParam(kern, list(tieWidth="inverseWidth"))
kernDisplay(kern)

ahonkela/tigre documentation built on Aug. 6, 2021, 12:08 p.m.